From nobody Thu Apr 2 20:38:41 2026 Received: from mail-dy1-f194.google.com (mail-dy1-f194.google.com [74.125.82.194]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 66A7923B62C for ; Sat, 14 Feb 2026 15:14:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.194 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771082044; cv=none; b=Che+bAxDr3y4nAtnzBItWpR00eokwe5gLNr9wickVRb4PZx4ql6yFADJU2t7z7470MCTqfYxl+qvsxYe5meJS35w71WactAQMhncBfsDNX5ZcEfzItcGVSeKPo2GPbttC6X8nvL22QtLcIRcpp51RX9Zs3PfHZAs2FqQA28/Qzc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771082044; c=relaxed/simple; bh=utSDcmkTYX81D6jOgekyFyBFWgL1XnSRDcyRfLLShTc=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:To:Cc; b=MEIgpryfkxSzZpYCBhWYmTcyoDd8Q6H/Tr0XxDjpItJmct28kFojHlsbi1LkE92WBWkTcoTojMyH4TtvgFgk0r2AOEcAwiaaP49s+13nz6+I0PgNXUZ0R9+mLIHS9nr5Gn9NJoze7G51Au/yvWd4NpP2+UUXuNJgqnBYvpzNAWE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=KQ6u9mi5; arc=none smtp.client-ip=74.125.82.194 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="KQ6u9mi5" Received: by mail-dy1-f194.google.com with SMTP id 5a478bee46e88-2bab70f8c8aso1864265eec.1 for ; Sat, 14 Feb 2026 07:14:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1771082042; x=1771686842; darn=vger.kernel.org; h=cc:to:message-id:content-transfer-encoding:mime-version:subject :date:from:from:to:cc:subject:date:message-id:reply-to; bh=Ty94LJlt9E6E68NvDEAdqXn4Y6wDb1z0/BuIy6B4NTA=; b=KQ6u9mi5hlK7hlV/eAZppfP4le4gm9VVq+931CRM4kqd0cyq4ON/iLALRQpuV0JyhJ CZzlNHFNKfQbrmrPMJ0sP6OW9Q2Eb6z5cDamDVWnLb8XsDp4mGlSx/Mi7qhv/I6Qqsab C7o68pwSrec95M+ZrxsbSSNcQR6Wr7PZaHG/a93SM6bROVB1O4OCixlC3MsgCNWZQvLG UGqoIZLwsdFHz8qGZJtnFSf0vcmliDqciod5WAdQS5hxLRXmWirzsHJWrFjzjpFavkjY rJgwcamw2S47fVhbC8iVtho2F4VS5MO9VOGMav1rgRqHMD+pXfXdjjRJYMzG/0aE8nCH ZsDw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1771082042; x=1771686842; h=cc:to:message-id:content-transfer-encoding:mime-version:subject :date:from:x-gm-gg:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to; bh=Ty94LJlt9E6E68NvDEAdqXn4Y6wDb1z0/BuIy6B4NTA=; b=GDDD1WUc5ecj31k6ujuJaF75l3jVWSwMYvWTFwPob2Yx+Bma+uJEZgqMfZ8/SbBnFj UgOcvZVg4rPnYlBq+d1fE5XU4r9T/hOpWtUm8pA0NdZnvmFOjNGoRSjwGjmiqnzmX9mc MJUls/n9dPyan4LyP71SojUn5Jq8e8l+tyhJrLc072/k3Y5pbQOQO/CASjxCpFdTbxc1 IrHdrfjWRMBYuMFD+3TdupkpM90Y/iNyhT7iyHcIs0xLfoV+PfKjVeGcAvV+JrLdeR5J ulRC6n6bj9iyovIqfTof6t5X4uw7HJ+mIs8+daVNEhaAYgGSISgHT4A0WKQr8wLdhvu9 aR5w== X-Forwarded-Encrypted: i=1; AJvYcCUdqCyBVhR6PFQyC9VnzM2A048BhB9ISq/2FKGMgFBLV2NM26gIS7i2lXGuYg50YV5SBok0iiR4RNlPyYI=@vger.kernel.org X-Gm-Message-State: AOJu0YxLzoocUM1l+NUDHkgCEQGtQNWYzxOrD0eOKRYY/cYLnrLAj2KT S3QKSNPwTwWfmIaVjcf1oeO4XB4Sn7hoiDZqhamADxKh7TitSHFsjxv1 X-Gm-Gg: AZuq6aKs/dHDUwXa2AoX9wdmHDcFquWPdwdmqHV75vM+vGhb2TNEwTa1dIoslmzDf42 JXbCihJ9Kh/fXMAZojd9HFewX9uzn3fJHhnmdsXWLpi6FmIPv/+dYK464avhKp5jKwBQTC3HaOf lxBSTa0YscNYqWc0Lq/VkcVUdwA5nzP7MpiyspbOaky6yK+wEgUK7t71cCj/0iBPkUyAX9Qxkdl /qH/7IeNeg3mgbej7AFejCV7Ga4DhDK2QyTxoSSl7HR67GD8Dg9gMOQI7mEZnkNVhHIk76/yTus U8gbfjTly7/t+ucnGLljiAaapjVdLHDGVuMMbywamgCyJfJvfoeLx82CHDlstowY7OgxhM5FBVu 5fqdKtVzHhSfajOTR6TLKO/EnFBvHBvbZTbHK3U9mMuhlLA1c8Ls7V2xYogkd1MX8Ov3ViD0082 31yWtUNls/pSrLdWRV X-Received: by 2002:a05:7300:e60d:b0:2ba:a075:540f with SMTP id 5a478bee46e88-2babc59bdbamr1962735eec.41.1771082042340; Sat, 14 Feb 2026 07:14:02 -0800 (PST) Received: from wujing. ([74.48.213.230]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-2bacb658544sm2667339eec.17.2026.02.14.07.13.55 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 14 Feb 2026 07:14:02 -0800 (PST) From: Qiliang Yuan Date: Sat, 14 Feb 2026 23:13:50 +0800 Subject: [PATCH v10] mm/page_alloc: boost watermarks on atomic allocation failure Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260214-wujing-mm-page_alloc-v8-v10-1-bdfea431fd97@gmail.com> X-B4-Tracking: v=1; b=H4sIAC2RkGkC/3XNSwrCMBQF0K1IxkbygbRx5D5EJP9GmqYkGpXSv ZsWB50U3uReuOdNIJvkTQbnwwSSKT77ONSA0fEAVCcGZ6DXtQAEEYYIYvD9evjBwRDgKJy5i76 PCpYWWol5w6VQzBpQ12My1n9W+nqrufP5GdN3/VTapf2bmOya9TDUQgraco6UphcXhO9PKgawm IVvHbrv8OoozbmlginZoK0zz/MPfPDI1gcBAAA= To: Andrew Morton , David Hildenbrand , Lorenzo Stoakes , "Liam R. Howlett" , Vlastimil Babka , Mike Rapoport , Suren Baghdasaryan , Michal Hocko , Axel Rasmussen , Yuanchu Xie , Wei Xu , Brendan Jackman , Johannes Weiner , Zi Yan , Lance Yang Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Qiliang Yuan X-Mailer: b4 0.13.0 Atomic allocations (GFP_ATOMIC) are prone to failure under heavy memory pressure as they cannot enter direct reclaim. Handle these failures by introducing a watermark boost mechanism for atomic requests. Refactor boost_watermark() using an internal helper to support both fragmentation and atomic paths. Apply zone-proportional boosts (~0.1% of managed pages) for atomic allocations, while decoupling it from watermark_boost_factor. Implement boost_zones_for_atomic() to iterate through and boost all eligible zones in the zonelist, respecting nodemasks. Use a per-zone 1-second debounce timer via last_boost_jiffies to prevent excessive boosting. Protect modifications with zone->lock and verify with lockdep. Integrate the mechanism into the page allocation slowpath specifically for order-0 GFP_ATOMIC requests. This approach reuses existing infrastructure and ensures emergency reserves even if fragmentation boosting is disabled. Allocation failure logs: [38535644.718700] node 0: slabs: 1031, objs: 43328, free: 0 [38535644.725059] node 1: slabs: 339, objs: 17616, free: 317 [38535645.428345] SLUB: Unable to allocate memory on node -1, gfp=3D0x48002= 0(GFP_ATOMIC) [38535645.436888] cache: skbuff_head_cache, object size: 232, buffer size: = 256, default order: 2, min order: 0 [38535645.447664] node 0: slabs: 940, objs: 40864, free: 144 [38535645.454026] node 1: slabs: 322, objs: 19168, free: 383 [38535645.556122] SLUB: Unable to allocate memory on node -1, gfp=3D0x48002= 0(GFP_ATOMIC) [38535645.564576] cache: skbuff_head_cache, object size: 232, buffer size: = 256, default order: 2, min order: 0 [38535649.655523] warn_alloc: 59 callbacks suppressed [38535649.655527] swapper/100: page allocation failure: order:0, mode:0x480= 020(GFP_ATOMIC), nodemask=3D(null) [38535649.671692] swapper/100 cpuset=3D/ mems_allowed=3D0-1 Acked-by: Vlastimil Babka Signed-off-by: Qiliang Yuan Acked-by: SeongJae Park --- v10: - Refactor watermark boosting into mechanism (__boost_watermark) and policy= logic. - Decouple Atomic boost from watermark_boost_factor to ensure emergency res= erves. - Simplify Atomic boost calculation to ~0.1% of managed pages with a 10% hi= gh-WM cap. - Boost all eligible zones in the zonelist while respecting nodemasks. v9: - Use mult_frac() for boost calculation. - Add !can_direct_reclaim check. - Code cleanup: naming, scope, and line limits. - Update tags: Add Vlastimil's Acked-by. - Link: https://lore.kernel.org/r/20260213-wujing-mm-page_alloc-v8-v9-1-cd9= 9f3a6cb70@gmail.com v8: - Use spin_lock_irqsave() to prevent inconsistent lock state. v7: - Use local variable for boost_amount. - Add zone->lock protection. - Add lockdep assertion. v6: - Use ATOMIC_BOOST_SCALE_SHIFT define. - Add documentation for 0.1% rationale. v5: - Use native boost_watermark(). v4: - Add watermark_scale_boost and gradual decay. v3: - Per-zone debounce timer. v2: - Debounce logic and zone-proportional boosting. v1: - Initial version. --- include/linux/mmzone.h | 1 + mm/page_alloc.c | 77 ++++++++++++++++++++++++++++++++++++++++++++--= ---- 2 files changed, 69 insertions(+), 9 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 75ef7c9f9307..8e37e4e6765b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -882,6 +882,7 @@ struct zone { /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; + unsigned long last_boost_jiffies; =20 unsigned long nr_reserved_highatomic; unsigned long nr_free_highatomic; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c380f063e8b7..9219bfca806b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2158,12 +2158,15 @@ bool pageblock_unisolate_and_move_free_pages(struct= zone *zone, struct page *pag =20 #endif /* CONFIG_MEMORY_ISOLATION */ =20 -static inline bool boost_watermark(struct zone *zone) +/* + * Helper for boosting watermarks. Called with zone->lock held. + * Use max_boost to limit the boost to a percentage of the high watermark. + */ +static inline bool __boost_watermark(struct zone *zone, unsigned long amou= nt, + unsigned long max_boost) { - unsigned long max_boost; + lockdep_assert_held(&zone->lock); =20 - if (!watermark_boost_factor) - return false; /* * Don't bother in zones that are unlikely to produce results. * On small machines, including kdump capture kernels running @@ -2173,9 +2176,6 @@ static inline bool boost_watermark(struct zone *zone) if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) return false; =20 - max_boost =3D mult_frac(zone->_watermark[WMARK_HIGH], - watermark_boost_factor, 10000); - /* * high watermark may be uninitialised if fragmentation occurs * very early in boot so do not boost. We do not fall @@ -2189,12 +2189,67 @@ static inline bool boost_watermark(struct zone *zon= e) =20 max_boost =3D max(pageblock_nr_pages, max_boost); =20 - zone->watermark_boost =3D min(zone->watermark_boost + pageblock_nr_pages, - max_boost); + zone->watermark_boost =3D min(zone->watermark_boost + amount, + max_boost); =20 return true; } =20 +/* + * Boost watermarks to increase reclaim pressure when fragmentation occurs + * and we fall back to other migratetypes. + */ +static inline bool boost_watermark(struct zone *zone) +{ + if (!watermark_boost_factor) + return false; + + return __boost_watermark(zone, pageblock_nr_pages, + mult_frac(zone->_watermark[WMARK_HIGH], + watermark_boost_factor, 10000)); +} + +/* + * Boost watermarks by ~0.1% of zone size on atomic allocation pressure. + * This provides zone-proportional safety buffers: ~1MB per 1GB of zone + * size. Max boost ceiling is fixed at ~10% of high watermark. + * + * This emergency reserve is independent of watermark_boost_factor. + */ +static inline bool boost_watermark_atomic(struct zone *zone) +{ + return __boost_watermark(zone, + max(pageblock_nr_pages, zone_managed_pages(zone) / 1000), + zone->_watermark[WMARK_HIGH] / 10); +} + +static void boost_zones_for_atomic(struct alloc_context *ac, gfp_t gfp_mas= k) +{ + struct zoneref *z; + struct zone *zone; + unsigned long now =3D jiffies; + + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { + /* Rate-limit boosts to once per second per zone */ + if (time_after(now, zone->last_boost_jiffies + HZ)) { + unsigned long flags; + bool should_wake; + + zone->last_boost_jiffies =3D now; + + /* Modify watermark under lock, wake kswapd outside */ + spin_lock_irqsave(&zone->lock, flags); + should_wake =3D boost_watermark_atomic(zone); + spin_unlock_irqrestore(&zone->lock, flags); + + if (should_wake) + wakeup_kswapd(zone, gfp_mask, 0, + ac->highest_zoneidx); + } + } +} + /* * When we are falling back to another migratetype during allocation, shou= ld we * try to claim an entire block to satisfy further allocations, instead of @@ -4742,6 +4797,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int = order, if (page) goto got_pg; =20 + /* Boost watermarks for atomic requests entering slowpath */ + if (((gfp_mask & GFP_ATOMIC) =3D=3D GFP_ATOMIC) && order =3D=3D 0 && !can= _direct_reclaim) + boost_zones_for_atomic(ac, gfp_mask); + /* * For costly allocations, try direct compaction first, as it's likely * that we have enough base pages and don't need to reclaim. For non- --- base-commit: b54345928fa1dbde534e32ecaa138678fd5d2135 change-id: 20260206-wujing-mm-page_alloc-v8-fb1979bac6fe Best regards, --=20 Qiliang Yuan